contacts_data.py

# contacts_data.py
"""
Contact database with 500 fake contacts covering all departments and divisions.
Each contact has Arabic and English names for better search support.
"""

from typing import List, Dict
from division_hierarchy import DIVISION_TO_DEPARTMENT
import random

# Common Arabic first names (male and female)
ARABIC_FIRST_NAMES_MALE = [
    "محمد", "أحمد", "عبدالله", "عمر", "خالد", "سعد", "فيصل", "سلطان", "ناصر", "طلال",
    "عبدالعزيز", "فهد", "تركي", "سلمان", "بندر", "مشعل", "ماجد", "يوسف", "حسن", "علي",
    "وليد", "زياد", "رامي", "كريم", "عادل", "راشد", "مازن", "طارق", "إبراهим", "عيسى",
    "نواف", "سامي", "بدر", "عاصم", "وسام", "هاني", "ثامر", "صالح", "ياسر", "جاسم",
    "هشام", "فواز", "معاذ", "عثمان", "أسامة", "باسل", "عمار", "نبيل", "توفيق", "جمال"
]

ARABIC_FIRST_NAMES_FEMALE = [
    "فاطمة", "نورة", "سارة", "منى", "هند", "ريم", "لينا", "دانة", "شهد", "جود",
    "رهف", "غلا", "عبير", "أمل", "ندى", "رنا", "لمى", "ديمة", "بشرى", "سمية",
    "هيفاء", "ليلى", "زينب", "خلود", "شروق", "أريج", "جميلة", "رباب", "سلمى", "وفاء",
    "عائشة", "خديجة", "مريم", "رقية", "زهراء", "نجود", "حصة", "عزة", "صفية", "ملاك",
    "روان", "تالا", "جنى", "لين", "ريتاج", "أسماء", "سديم", "لمار", "بيان", "شيماء"
]

# Common Arabic last names
ARABIC_LAST_NAMES = [
    "العتيبي", "الدوسري", "القحطاني", "الشهري", "الغامدي", "الزهراني", "العنزي", "الحربي",
    "المطيري", "العسيري", "السبيعي", "الشمري", "الجهني", "العمري", "البقمي", "الفهد",
    "السديري", "الثبيتي", "الصقري", "الأحمد", "الخالد", "السليمان", "العبدالله", "الفهيد",
    "الشايع", "الرشيد", "العجمي", "المالك", "الفريح", "الحمود", "الناصر", "الشريف",
    "البلوي", "اليامي", "الوادعي", "الفيفي", "الشهراني", "البكري", "العسكر", "الراشد",
    "الفايز", "الخليف", "المنيع", "العبيد", "السحيم", "الغنام", "السلمان", "الهاجري",
    "النهدي", "الرويلي", "المري", "السواط", "الربيعان", "الدغيثر", "الفضلي", "القرني",
    "الثنيان", "العريفي", "الهويدي", "الجريسي", "البدراني", "المهيدب", "السالم", "الحارثي",
    "العطوي", "الصخري", "الرحيلي", "السعيد", "الحافظ", "الوهيبي", "البراك", "الضويان"
]

# Job titles in English and Arabic by category
JOB_TITLES = {
    "executive": [
        ("Chief Executive Officer", "المدير التنفيذي"),
        ("Executive Director", "المدير التنفيذي"),
        ("Vice President", "نائب الرئيس"),
        ("Senior Vice President", "نائب الرئيس الأول"),
    ],
    "management": [
        ("Director", "مدير"),
        ("Senior Manager", "مدير أول"),
        ("Manager", "مدير"),
        ("Assistant Manager", "مساعد مدير"),
        ("Team Leader", "قائد فريق"),
        ("Supervisor", "مشرف"),
    ],
    "specialist": [
        ("Senior Specialist", "أخصائي أول"),
        ("Specialist", "أخصائي"),
        ("Senior Analyst", "محلل أول"),
        ("Analyst", "محلل"),
        ("Senior Consultant", "مستشار أول"),
        ("Consultant", "مستشار"),
        ("Senior Officer", "موظف أول"),
        ("Officer", "موظف"),
    ],
    "technical": [
        ("Senior Engineer", "مهندس أول"),
        ("Engineer", "مهندس"),
        ("Technical Lead", "قائد تقني"),
        ("Developer", "مطور"),
        ("Architect", "مهندس معماري"),
    ],
    "support": [
        ("Coordinator", "منسق"),
        ("Administrator", "إداري"),
        ("Assistant", "مساعد"),
        ("Associate", "معاون"),
    ]
}

# Phone extensions (4-digit)
def generate_extension() -> str:
    """Generate a 4-digit phone extension"""
    return str(random.randint(1000, 9999))

# Email generation
def generate_email(first_name_en: str, last_name_en: str) -> str:
    """Generate an email address"""
    # Remove spaces and special characters
    first = first_name_en.lower().replace(" ", "").replace("-", "")
    last = last_name_en.lower().replace(" ", "").replace("-", "")
    return f"{first}.{last}@sidf.gov.sa"


def transliterate_arabic_name(arabic_name: str) -> str:
    """
    Simple transliteration of Arabic names to English.
    This is a basic mapping for common names.
    """
    transliteration_map = {
        # Male names
        "محمد": "Mohammed", "أحمد": "Ahmed", "عبدالله": "Abdullah", "عمر": "Omar", "خالد": "Khalid",
        "سعد": "Saad", "فيصل": "Faisal", "سلطان": "Sultan", "ناصر": "Nasser", "طلال": "Talal",
        "عبدالعزيز": "Abdulaziz", "فهد": "Fahad", "تركي": "Turki", "سلمان": "Salman", "بندر": "Bandar",
        "مشعل": "Mishaal", "ماجد": "Majed", "يوسف": "Yousef", "حسن": "Hassan", "علي": "Ali",
        "وليد": "Waleed", "زياد": "Ziyad", "رامي": "Rami", "كريم": "Kareem", "عادل": "Adel",
        "راشد": "Rashed", "مازن": "Mazen", "طارق": "Tariq", "إبراهim": "Ibrahim", "عيسى": "Issa",
        "نواف": "Nawaf", "سامي": "Sami", "بدر": "Badr", "عاصم": "Asim", "وسام": "Wissam",
        "هاني": "Hani", "ثامر": "Thamer", "صالح": "Saleh", "ياسر": "Yasser", "جاسم": "Jasim",
        "هشام": "Hisham", "فواز": "Fawaz", "معاذ": "Muath", "عثمان": "Othman", "أسامة": "Osama",
        "باسل": "Basel", "عمار": "Ammar", "نبيل": "Nabil", "توفيق": "Tawfiq", "جمال": "Jamal",

        # Female names
        "فاطمة": "Fatima", "نورة": "Noura", "سارة": "Sarah", "منى": "Mona", "هند": "Hind",
        "ريم": "Reem", "لينا": "Lina", "دانة": "Dana", "شهد": "Shahad", "جود": "Joud",
        "رهف": "Rahaf", "غلا": "Ghala", "عبير": "Abeer", "أمل": "Amal", "ندى": "Nada",
        "رنا": "Rana", "لمى": "Lama", "ديمة": "Dima", "بشرى": "Bushra", "سمية": "Somaya",
        "هيفاء": "Haifa", "ليلى": "Layla", "زينب": "Zainab", "خلود": "Kholoud", "شروق": "Shorouq",
        "أريج": "Areej", "جميلة": "Jamila", "رباب": "Rabab", "سلمى": "Salma", "وفاء": "Wafa",
        "عائشة": "Aisha", "خديجة": "Khadija", "مريم": "Maryam", "رقية": "Ruqaya", "زهراء": "Zahra",
        "نجود": "Nujoud", "حصة": "Hessa", "عزة": "Azza", "صفية": "Safiya", "ملاك": "Malak",
        "روان": "Rawan", "تالا": "Tala", "جنى": "Jana", "لين": "Leen", "ريتاج": "Ritaj",
        "أسماء": "Asma", "سديم": "Sadeem", "لمار": "Lamar", "بيان": "Bayan", "شيماء": "Shaima",

        # Last names
        "العتيبي": "Al-Otaibi", "الدوسري": "Al-Dosari", "القحطاني": "Al-Qahtani", "الشهري": "Al-Shahri",
        "الغامدي": "Al-Ghamdi", "الزهراني": "Al-Zahrani", "العنزي": "Al-Anazi", "الحربي": "Al-Harbi",
        "المطيري": "Al-Mutairi", "العسيري": "Al-Asiri", "السبيعي": "Al-Subaie", "الشمري": "Al-Shammari",
        "الجهني": "Al-Juhani", "العمري": "Al-Omari", "البقمي": "Al-Buqami", "الفهد": "Al-Fahad",
        "السديري": "Al-Sudairi", "الثبيتي": "Al-Thubaiti", "الصقري": "Al-Saqri", "الأحمد": "Al-Ahmad",
        "الخالد": "Al-Khalid", "السليمان": "Al-Sulaiman", "العبدالله": "Al-Abdullah", "الفهيد": "Al-Fahaid",
        "الشايع": "Al-Shaya", "الرشيد": "Al-Rasheed", "العجمي": "Al-Ajmi", "المالك": "Al-Malek",
        "الفريح": "Al-Fraihi", "الحمود": "Al-Hamoud", "الناصر": "Al-Nasser", "الشريف": "Al-Shareef",
        "البلوي": "Al-Balawi", "اليامي": "Al-Yami", "الوادعي": "Al-Wadei", "الفيفي": "Al-Faifi",
        "الشهراني": "Al-Shahrani", "البكري": "Al-Bakri", "العسكر": "Al-Askar", "الراشد": "Al-Rashed",
        "الفايز": "Al-Fayez", "الخليف": "Al-Khleif", "المنيع": "Al-Manie", "العبيد": "Al-Obaid",
        "السحيم": "Al-Suhaim", "الغنام": "Al-Ghannam", "السلمان": "Al-Salman", "الهاجري": "Al-Hajri",
        "النهدي": "Al-Nahdi", "الرويلي": "Al-Ruwaili", "المري": "Al-Marri", "السواط": "Al-Sawat",
        "الربيعان": "Al-Rabian", "الدغيثر": "Al-Dughither", "الفضلي": "Al-Fadhli", "القرني": "Al-Qarni",
        "الثنيان": "Al-Thuniyan", "العريفي": "Al-Arifi", "الهويدي": "Al-Huwaidi", "الجريسي": "Al-Juraysi",
        "البدراني": "Al-Badrani", "المهيدب": "Al-Muhaidib", "السالم": "Al-Salem", "الحارثي": "Al-Harthi",
        "العطوي": "Al-Atawi", "الصخري": "Al-Sakhri", "الرحيلي": "Al-Rahili", "السعيد": "Al-Saeed",
        "الحافظ": "Al-Hafiz", "الوهيبي": "Al-Wahaibi", "البراك": "Al-Barrak", "الضويان": "Al-Dhuwayan",
    }
    return transliteration_map.get(arabic_name, arabic_name)


def generate_contacts() -> List[Dict]:
    """
    Generate 500 fake contacts distributed across all divisions.
    Returns a list of contact dictionaries.
    """
    contacts = []
    contact_id = 1000  # Starting ID

    # Get all divisions
    divisions = list(DIVISION_TO_DEPARTMENT.keys())

    # Calculate contacts per division (aim for ~7-8 per division)
    contacts_per_division = 500 // len(divisions)
    extra_contacts = 500 % len(divisions)

    for div_index, division in enumerate(divisions):
        department_name, department_id = DIVISION_TO_DEPARTMENT[division]

        # Number of contacts for this division
        num_contacts = contacts_per_division
        if div_index < extra_contacts:
            num_contacts += 1

        # Determine seniority distribution (more junior staff than senior)
        # 10% executive, 20% management, 50% specialist, 15% technical, 5% support
        seniority_distribution = []
        seniority_distribution.extend(["executive"] * max(1, int(num_contacts * 0.10)))
        seniority_distribution.extend(["management"] * max(1, int(num_contacts * 0.20)))
        seniority_distribution.extend(["specialist"] * max(1, int(num_contacts * 0.50)))
        seniority_distribution.extend(["technical"] * max(1, int(num_contacts * 0.15)))
        seniority_distribution.extend(["support"] * max(1, int(num_contacts * 0.05)))

        # Ensure we have exactly num_contacts
        while len(seniority_distribution) < num_contacts:
            seniority_distribution.append("specialist")
        seniority_distribution = seniority_distribution[:num_contacts]

        random.shuffle(seniority_distribution)

        for i in range(num_contacts):
            # Mix male and female names (60% male, 40% female)
            is_male = random.random() < 0.6

            if is_male:
                first_name_ar = random.choice(ARABIC_FIRST_NAMES_MALE)
            else:
                first_name_ar = random.choice(ARABIC_FIRST_NAMES_FEMALE)

            last_name_ar = random.choice(ARABIC_LAST_NAMES)

            # Transliterate to English
            first_name_en = transliterate_arabic_name(first_name_ar)
            last_name_en = transliterate_arabic_name(last_name_ar)

            # Full names
            full_name_ar = f"{first_name_ar} {last_name_ar}"
            full_name_en = f"{first_name_en} {last_name_en}"

            # Get job title based on seniority
            seniority = seniority_distribution[i]
            title_en, title_ar = random.choice(JOB_TITLES[seniority])

            # Generate contact info
            extension = generate_extension()
            email = generate_email(first_name_en, last_name_en)

            contact = {
                "id": contact_id,
                "first_name_ar": first_name_ar,
                "last_name_ar": last_name_ar,
                "full_name_ar": full_name_ar,
                "first_name_en": first_name_en,
                "last_name_en": last_name_en,
                "full_name_en": full_name_en,
                "title_en": title_en,
                "title_ar": title_ar,
                "division": division,
                "department": department_name,
                "department_id": department_id,
                "email": email,
                "extension": extension,
                "phone": f"+966-11-218-{extension}",
            }

            contacts.append(contact)
            contact_id += 1

    return contacts


# Generate contacts on module load
CONTACTS_DATABASE = generate_contacts()

# Create indexes for fast lookup
CONTACTS_BY_NAME_AR = {contact["full_name_ar"]: contact for contact in CONTACTS_DATABASE}
CONTACTS_BY_NAME_EN = {contact["full_name_en"]: contact for contact in CONTACTS_DATABASE}
CONTACTS_BY_DIVISION = {}
for contact in CONTACTS_DATABASE:
    division = contact["division"]
    if division not in CONTACTS_BY_DIVISION:
        CONTACTS_BY_DIVISION[division] = []
    CONTACTS_BY_DIVISION[division].append(contact)


def get_all_contacts() -> List[Dict]:
    """Get all contacts"""
    return CONTACTS_DATABASE


def get_contacts_by_division(division: str) -> List[Dict]:
    """Get contacts for a specific division"""
    return CONTACTS_BY_DIVISION.get(division, [])


def get_contact_by_name(name: str) -> Dict:
    """Get contact by exact name (Arabic or English)"""
    # Try Arabic first
    contact = CONTACTS_BY_NAME_AR.get(name)
    if contact:
        return contact

    # Try English
    contact = CONTACTS_BY_NAME_EN.get(name)
    if contact:
        return contact

    return None


if __name__ == "__main__":
    # Test the contact generation
    contacts = get_all_contacts()
    print(f"Generated {len(contacts)} contacts")
    print(f"\nSample contacts:")
    for i, contact in enumerate(contacts[:5]):
        print(f"{i+1}. {contact['full_name_en']} ({contact['full_name_ar']})")
        print(f"   {contact['title_en']} - {contact['division']}")
        print(f"   {contact['email']} | Ext: {contact['extension']}")
        print()

    # Show distribution by department
    from collections import Counter
    dept_counts = Counter(contact["department"] for contact in contacts)
    print("\nContacts by Department:")
    for dept, count in sorted(dept_counts.items(), key=lambda x: -x[1]):
        print(f"  {dept}: {count}")